The influence of perceptual training on working memory in older adults

Abstract

Normal aging is associated with a degradation of perceptual abilities and a decline in higher-level cognitive functions, notably working memory. To remediate age-related deficits, cognitive training programs are increasingly being developed. However, it is not yet definitively established if, and by what mechanisms, training ameliorates effects of cognitive aging. Furthermore, a major factor impeding the success of training programs is a frequent failure of training to transfer benefits to untrained abilities. Here, we offer the first evidence of direct transfer-of-benefits from perceptual discrimination training to working memory performance in older adults. Moreover, using electroencephalography to evaluate participants before and after training, we reveal neural evidence of functional plasticity in older adult brains, such that training-induced modifications in early visual processing during stimulus encoding predict working memory accuracy improvements. These findings demonstrate the strength of the perceptual discrimination training approach by offering clear psychophysical evidence of transfer-of-benefit and a neural mechanism underlying cognitive improvement.

Figure 1. Perceptual discrimination.

1a. Perceptual discrimination training paradigm. Gabor pattern filters required a discrimination judgment of whether the stimuli expanded or contracted. Training was adaptive, such that changes in the ISI and stimuli duration scaled with performance. 1b. Training effects on trained task. Trained older adults showed significant improvement over untrained controls at medium and high difficulty tasks (100 ms and 50 ms stimuli and ISI duration, respectively). 1c. Untrained perceptual discrimination paradigm. Discrimination thresholds for direction of 100% coherent motion was tested using moving dot kinetograms. Participants made a judgment as to whether two presented directions of motion matched one another. 1d. Training effects on untrained task. Perceptual discrimination thresholds of trained older adults improved significantly more than untrained controls. * Asterisks indicate significant differences within group from T1 to T2 (paired t-test). Crosses indicates significant group by time interactions (repeated measures ANOVA).

Figure 2. Working memory paradigm.

Delayed-recognition paradigm. Working memory for the direction of 100% coherent motion was tested using moving dot kinetograms in two tasks. Participants encoded a direction of motion (cue) and after a delay period determined if the probe direction matched the cue direction. In the Interrupting stimuli task (IS), a circular swirl of motion was presented in the middle of delay period. A button press was required if the swirl was fast. A third task was perceptually equivalent to the WM tasks, but participants were instructed to passively view stimuli and press a right or left button at probe depending on the direction of an arrow.

Figure 3. Working memory performance.

At T2, WM was tested on the NI and IS tasks at the participant's original perceptual threshold (obtained at T1) and new threshold (obtained at T2). Change in WM accuracy was calculated as T2 – T1. Training led to WM improvement in the NI task compared to controls when tested at their original threshold (training effect). Neither group showed changes in WM performance when tested at their new perceptual threshold. Both groups improved in the IS task at the original threshold (practice effect), but not at the new threshold. * Asterisks indicate significant differences within group from T1 to T2 (paired t-test). Crosses indicates significant group by time interactions (repeated measures ANOVA).

Figure 4. EEG Recordings.

Event-Related Potentials during stimulus encoding. Posterior occipital N1 amplitude (120–220 ms) significantly decreased at T2 for the training, but not control group. Statistics are based on electrode of interest (EOI) clusters selected for each participant. Scalp topographies of T2-T1 at the latency of mean N1 peak +/− 1sd illustrate the location of the training related functional plasticity.

Figure 5. Neural-behavioral correlation.

Across participants, decreased N1 amplitude during encoding correlated with WM performance improvements in the NI task at the original threshold in the training group (r = 0.82, p<0.001).